PubMed Articles Scraper
Pricing
from $1.86 / 1,000 item extracteds
Go to Apify Store
PubMed Articles Scraper
Search PubMed and export normalized article metadata and abstracts for literature reviews and research monitoring.
PubMed Articles Scraper
Pricing
from $1.86 / 1,000 item extracteds
Search PubMed and export normalized article metadata and abstracts for literature reviews and research monitoring.
You can access the PubMed Articles Scraper programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, youβll need an Apify account and your API token, found in API & Integrations in Apify Console.
{ "openapi": "3.0.1", "info": { "version": "0.1", "x-build-id": "TQF83SdDDvgOe9A2w" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/automation-lab~pubmed-article-search-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-automation-lab-pubmed-article-search-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/automation-lab~pubmed-article-search-scraper/runs": { "post": { "operationId": "runs-sync-automation-lab-pubmed-article-search-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/automation-lab~pubmed-article-search-scraper/run-sync": { "post": { "operationId": "run-sync-automation-lab-pubmed-article-search-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "required": [ "queries" ], "properties": { "queries": { "title": "PubMed search queries", "minItems": 1, "maxItems": 20, "type": "array", "description": "One or more PubMed queries. Standard PubMed field tags and Boolean operators are supported, for example Alzheimer disease[MeSH Terms] AND review[Publication Type].", "default": [ "CRISPR cancer" ], "items": { "type": "string" } }, "maxItems": { "title": "Maximum articles", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Maximum number of unique article records saved across all queries. Duplicate PMIDs found by multiple queries count once.", "default": 100 }, "sort": { "title": "Sort order", "enum": [ "relevance", "pub_date" ], "type": "string", "description": "Order returned by PubMed: best match relevance or newest publication date first.", "default": "relevance" }, "minDate": { "title": "Earliest publication date", "pattern": "^\\d{4}\\/\\d{2}\\/\\d{2}$", "type": "string", "description": "Optional inclusive publication-date boundary in YYYY/MM/DD format." }, "maxDate": { "title": "Latest publication date", "pattern": "^\\d{4}\\/\\d{2}\\/\\d{2}$", "type": "string", "description": "Optional inclusive publication-date boundary in YYYY/MM/DD format." }, "articleTypes": { "title": "Publication types", "maxItems": 20, "type": "array", "description": "Optional exact PubMed publication types, such as Review, Clinical Trial, or Meta-Analysis. Values are combined with AND filters.", "default": [], "items": { "type": "string" } }, "journals": { "title": "Journals", "maxItems": 20, "type": "array", "description": "Optional journal names to require, such as The Lancet or Nature Medicine. Values are combined with AND filters.", "default": [], "items": { "type": "string" } }, "includeAbstract": { "title": "Include abstracts", "type": "boolean", "description": "Include abstract text when PubMed provides it. Disabling this reduces dataset size but does not change request count.", "default": true }, "includeMeshTerms": { "title": "Include MeSH terms", "type": "boolean", "description": "Include Medical Subject Headings assigned to each article when available.", "default": true }, "apiKey": { "title": "NCBI API key", "type": "string", "description": "Optional personal NCBI API key. It permits a higher request rate but is not required for normal runs." }, "email": { "title": "Contact email for NCBI", "type": "string", "description": "Optional contact email sent to NCBI E-utilities as recommended for larger automated requests." } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } } } } } } } }}OpenAPI is a standard for designing and describing RESTful APIs, allowing developers to define API structure, endpoints, and data formats in a machine-readable way. It simplifies API development, integration, and documentation.
OpenAPI is effective when used with AI agents and GPTs by standardizing how these systems interact with various APIs, for reliable integrations and efficient communication.
By defining machine-readable API specifications, OpenAPI allows AI models like GPTs to understand and use varied data sources, improving accuracy. This accelerates development, reduces errors, and provides context-aware responses, making OpenAPI a core component for AI applications.
You can download the OpenAPI definitions for PubMed Articles Scraper from the options below:
If youβd like to learn more about how OpenAPI powers GPTs, read our blog post.
You can also check out our other API clients: